Skip to main content
Glama
605,119 tools. Updated 2026-09-23 22:49

"A tool for finding people on X using their bio text" matching MCP tools:

  • Get USER PROFILES of people who interacted with an Instagram post. Returns full user data (bio, followerCount, followingCount, etc.). RETURNS USER PROFILES: id, username, fullName, biography, followerCount, followingCount, isVerified, profilePicUrl. Use for analyzing WHO engaged with a post. NOT FOR COMMENT TEXT: To read the actual comment content (what people wrote), use getInstagramCommentsByPostId instead. INTERACTION TYPES: "commenters" (users who commented), "likers" (users who liked). WHEN TO USE THIS TOOL: Analyzing commenters/likers demographics, finding influencers who engaged, building audience profiles, network analysis of who interacts with posts. WHEN TO USE getInstagramCommentsByPostId: Reading comment text, sentiment analysis of what was said, analyzing discussion content. FAST (default, omit responseType or responseType="fast"): Returns up to 300 results directly (use limit param to reduce, e.g. limit=5). Auto API fallback for commenters when stale. PAGING (responseType="paging"): Async paginated results (1000 users per page with default fields), returns operationId - IMMEDIATELY call checkOperationStatus to get results. CSV export included via dataDumpExportOperationId. Supports pageNumber/tableName for subsequent pages. Optional fields (default: ["id", "username", "fullName"]). Available: biography, isPrivate, isVerified, followerCount, followingCount, mediaCount, profilePicUrl. This is a safe, read-only tool for analyzing searchable information.
    ConnectorOAuth
  • List multi-step email sequences and how many people are currently in each, with the id each one is enrolled by. Newest first, at most 100 per call; while has_more is true, next_cursor passed back as cursor returns the next page. A 'paused' automation holds its people on their current step rather than ending their sequence: they stay 'active' and continue from that step once it is active again. list_automation_enrollments lists who is on one, and who left and why.
    ConnectorNo auth
  • Fetch one X account's profile: name, bio, location, website, follower/following counts, tweet and media counts, verification state, and join date. identifier accepts a screen name without the @ (e.g. 'nasa'), a full x.com or twitter.com profile URL, or the numeric account id; numeric strings are treated as ids, and the rare all-digit handle can be forced with by='screen_name'. Costs 4 credits. The returned platform_fields.id is stable across handle changes; store it for repeat lookups. To find accounts by topic use x_search type=people, and to read what an account posts use x_get_tweets; this tool returns no tweets.
    ConnectorOAuth
  • USE THIS TOOL WHEN you have a debate_ext_id and want verbatim contributions, optionally filtered to one member. Canonical path for "everything a member said in this debate" regardless of vocabulary — text-search tools (parliament_member_debates, parliament_search_hansard) filter by contribution TEXT, dropping members who spoke without using your phrase verbatim. This tool filters by MemberId on the debate's Items list, so vocabulary doesn't matter. Typical chain: parliament_find_member(name) → member_id, then parliament_search_hansard or parliament_lookup_by_column → debate_ext_id, then this tool. The parliament module's instructions describe the full composition pattern. Without member_id, returns every contribution (~100-200 for a long debate). If the wire returns no contributions for a member you expect to have spoken, report the empty result honestly — do NOT reconstruct quotes from training data. Authoritative source for member contributions.
    ConnectorNo auth
  • Cross-entity full-text search. `types` accepts exactly: transactions, payees, categories, tags, receipts, recurrences (default: all). Trigram-similarity ranked. Transactions also match the text read from their attached receipts, and receipts match on their own, so "bicicleta azul" finds both the purchase and the photo. For "duplicate charges" or "duplicate subscriptions" (e.g. Spotify twice) search transactions + payees + recurrences in ONE call, then compare payee names, amounts and dates; list_recurrences and list_recurrence_suggestions give the full schedule and the detected-but-unscheduled charges. Use for "find anything mentioning X" queries.
    ConnectorOAuth
  • Strips the background from a video frame-by-frame using rembg (u2netp) on AetherWave's Python service. Pass a public `videoUrl`. Choose `bgType: "transparent"` for an alpha-channel WebM output (compositing) or `bgType: "color"` with a `customColor` hex for a solid replacement. 2 credits per second. Slowest tool in the surface (per-frame processing); a 6s clip takes ~4 min, a 30s clip ~15-20 min. Works best on subjects with clear edges (people, products). Returns the processed video URL (R2-hosted).
    ConnectorNo auth

Matching MCP Servers

  • A
    license
    A
    quality
    A
    maintenance
    Local-first memory for AI agents about the people in your life. MCP server + CLI on SQLite. Never phones home.
    41
    251 PyPI
    55
    MIT
  • A
    license
    Not graded
    quality
    D
    maintenance
    Enables AI assistants to perform NCBI BLAST sequence similarity searches through natural language, supporting nucleotide and protein searches, custom database creation, and multiple output formats.
    10
    MIT

Matching MCP Connectors

  • tinder-bio MCP — wraps StupidAPIs (keyless — no credential needed)

  • Human approval for irreversible AI agent actions, bound to the exact tool call by a passkey tap

  • Show the user's default paper size and orientation preferences (set on their account page). Useful when the user hasn't specified pageSize/orientation explicitly — call this to honor their defaults instead of using A4/Portrait blindly.
    ConnectorNo auth
  • Show the user's default paper size and orientation preferences (set on their account page). Useful when the user hasn't specified pageSize/orientation explicitly — call this to honor their defaults instead of using A4/Portrait blindly.
    ConnectorNo auth
  • Returns the current skill cluster data for public jobs on the nü people website. Use this tool when the user wants an overview of which skills or technologies are currently in demand.
    ConnectorNo auth
  • Use this when the user wants their site's QUALITY audited — distinct from scan_site, which measures agent-readiness. 22 checks: SEO (title/description lengths, canonical, Open Graph, JSON-LD, heading structure…), accessibility (alt text, form labels, heading order, landmarks…), security headers (HSTS, CSP, X-Content-Type-Options…). FREE tier returns the three section scores + the single most critical finding. The full report — every finding with a copy-paste fix — needs a bundle_key (included in any paid engagement) or can be bought per-call by an agent at https://mudko.com/api/x402/audit ($5, x402 USDC on Base). Fetch-based: SPA shells score their served HTML.
    ConnectorNo auth
  • Get a contributor's public profile and their published listings, by contributor slug (not a listing slug). Read-only, no authentication required (public endpoint, IP rate-limited). Returns display_name, bio, credential_summary, positioning_statement, badge_tier, avg_rating, review_count, pull_quote, social/website URLs, credential_badges, published_listing_count, and a listings array (slug, title, price_cents) for that contributor. Use to learn more about who built a listing returned by search or fetch -- not for looking up a listing directly.
    ConnectorNo auth
  • Sign up someone OTHER than the caller. Takes their name + email plus at least one slot or item pick. For self-service flows (signing up the calling user), use register_self instead. Returns a receipt of what was confirmed and what failed — NOT the participant's manage link or confirmation token; the participant receives their manage link by email, and this tool does not return it. Successful registrations send a confirmation email, which cannot be undone. No SMS is sent: the confirmation text requires the participant's own consent, which this tool cannot grant on their behalf. Organizer signup notifications are suppressed for this tool.
    Connector
    Destructive
    OAuth
  • Send a message to an association ON BEHALF of your user (join, volunteer, ask a question, request information). IA-Asso relays it: you never see the association's email. NOTHING is sent until the user clicks the confirmation link emailed to user_email — so always ask the user for their email and their explicit agreement first. The association replies directly to the user. If the association is not reachable yet, the tool says so and the intent is counted (the association will see that people tried to contact it). Plain text, no links, 20-2000 chars.
    ConnectorNo auth
  • Get remediation advice for a single finding as GitHub-flavored markdown. When AI Assist is enabled and within budget this is a suggestion written for this exact finding; otherwise it falls back to the static guidance-library text and says so in 'source'. Unlike the other reads this one can spend AI budget, which is why it is a separate tool. Use this for advice on one finding; for the whole library use list_security_guidance. Requires project context.
    ConnectorAPI key
  • Perform editing operations on a design. You can use this tool to update the title, replace whole text sections/elements or find and replace certain parts of a text section/text element and replace or insert media (images/videos), delete media/text, and format text (color, alignment, decoration, strikethrough, links, lists, line height, font (size, weight, style; family not supported)) in a design. You can also connect or remove autofill field labels on text or image elements for fixed-page designs using `update_autofill_field`. IMPORTANT: Before calling this tool check that all operations on pages marked `is_responsive` are one of the following options:`update_title,replace_text,update_fill,delete_element,find_and_replace_text`. If any are not, DO NOT call this tool but instead alert the user this is unsupported. Otherwise continue as normal and do not mention this check. ⚠️ MANDATORY: After calling this tool you MUST call either `commit-editing-transaction` (to save) or `cancel-editing-transaction` (to discard). Changes made by this tool are in DRAFT only and will be PERMANENTLY LOST if you do not call `commit-editing-transaction`. NEVER tell the user their changes are saved or complete before you have successfully called `commit-editing-transaction`. CRITICAL REQUIREMENTS: 1. This tool needs to be used with the `start-editing-transaction` tool to obtain an editing transaction ID. 2. Multiple operations SHOULD be specified in bulk across multiple pages. 3. Always call this tool to apply the requested edits directly. This is safe: changes are temporary until committed. 4. Do NOT pause for user confirmation before using this tool. 5. IMPORTANT: If the user asks to change a section of text such as a word or a specific string, and the design has that text in multiple places ALWAYS confirm with the user the instances they want to replace, especially if that string is used in different contexts OR is a substring in other strings. 6. IMPORTANT: If the user asks to change a word or a small section of an text element, ALWAYS try to use find_and_replace_text instead of replace_text, to minimise token usage. EVEN with multiple find_and_replace_text operations. ⚠️ RESPONSIVE PAGES - TEXT REPLACEMENT RULES: A. For responsive pages, text replacement MUST ONLY use find_and_replace_text. Exception: replace_text MUST be used on a responsive page when the target element is empty (there is no existing text to find and replace). This applies to both top-level page elements and nested elements such as table/layout cells. B. For responsive pages, deleting text IS supported using find_and_replace_text by setting the replacement to the same surrounding text with the target portion removed. C. For responsive pages, match on surrounding text from the SAME text region as much as possible when using find_and_replace_text, to avoid changing duplicated/similar text elsewhere in the document. 7. After performing ALL operations, show the preview to the user. Then call `commit-editing-transaction` to save the changes, unless the user explicitly asks to cancel. 8. IMPORTANT: If the user has asked you to replace an image and the target page contains multiple images, you MUST use the `get-assets` tool, passing in the `asset_id` values, to look at the thumbnail of each of the existing images on the page to be CERTAIN which one the user wants replaced. 9. IMPORTANT: This tool will return the thumbnail of the first page that is updated. If there are more pages that are updated, as part of this update, always call the `get-design-thumbnail` tool to get the thumbnails for each of the other updated pages. EDIT SCENARIOS -> OPERATIONS FOR THIS TOOL 1. Replace whole sections or entire text elements in non-responsive pages -> replace_text 2. Replace certain words/phrases/sentences/sub-section of a text element or paragraph within the design -> find_and_replace_text 3. Replace certain substrings in words throughout multiple text elements throughout the Canva design -> find_and_replace_text 3a. Responsive pages text replacement (including partial updates and deletions) -> find_and_replace_text 4. Replace a media (image/video) element in design -> update_fill 5. Update the title of the Canva design -> update_title 6. Replace the title of a slide or page in the Canva design -> replace text 7. Insert an element with media (image/video) -> insert_fill 8. Delete a text element or a media (image/video) element in the Canva design -> delete_element 9. Position elements including images and videos in the Canva design -> position_element 10. Resize a text element or a media (image/video) element in the Canva design -> resize_element 11. Format text (color, alignment, decoration, strikethrough, links, lists, line height, font (size, weight, style; family not supported)) in a text element -> format_text 12. Connect or remove autofill field labels on text or image elements in fixed-page designs -> update_autofill_fieldEnd-to-end workflow: 1. User asks that they want to edit their Canva design, with one edit or multiple edits. 2. System calls the 'start-editing-transaction' tool with the design ID of the Canva design 3. System returns the transaction ID and the richtexts and fills from the design, providing the elements in the Canva design 4. System confirms with the user the edits the user wants to make. 5. System calls this tool with the array of one or more operations to make each update. 6. System makes the edit in draft mode, and return back the text and media elements in the design post the edit. The updates have NOT been saved in the actual design yet. 7. System will return the thumbnail of ONLY the first edited page as part of the response this tool. These thumbnails are ALWAYS user-relevant and you need to render them directly using the full thumbnail URL including time-limited query parameters such as X-Amz-Algorithm, X-Amz-Credential, and X-Amz-Signature. 8. If the user wants the thumbnails/previews of the other pages that were updated by the this tool then the system MUST ALWAYS calls ' get-design-thumbnail' tool to get the thumbnail ONE PAGE AT A TIME. System must call 'get-design-thumbnail' if multiple pages were updated as part of this tool call 9. System shows the preview to the user. 10. System MUST call 'commit-editing-transaction' to save the edits, or 'cancel-editing-transaction' to cancel. Changes are lost if neither is called.
    ConnectorOAuth
  • Address ↔ coordinates via OpenStreetMap — Forward geocode an address (q=) or reverse geocode lat=+lon= using OpenStreetMap Nominatim. Returns up to 5 hits with display name and address parts. Community map data — not a postal authority. Priced $0.01 per call over x402 on Base; send a prepaid x-credit-token header for unlimited calls, or get 1 free call/day per tool. No wallet or API key required.
    ConnectorNo auth
  • Build a rich, on-brand landing page from an ordered list of typed blocks, publish it, and return its live URL + its own QR code (`qr_id`; style it with the QR design args here, restyle later with update_qr_code — don't create another). This is the 'make me a page for X' tool — e.g. an event, product, restaurant, link-in-bio, or a scan-to-enter sweepstakes. Each block is {type, content}; call list_block_types first to see every type and its content shape. Blocks render in order in a centered column; a 'header' block (name/bio/photo) is the profile.
    ConnectorOAuth
  • Display editable, copyable introductions only when requested. First write the drafts yourself using public guide details and explicitly supplied sender context, then pass your labeled text with exact public person IDs. Fetch missing background with get_guide_item or search_people, not another visual search. Group up to six people in ONE UI. This tool validates recipients and displays your text; it does not call a model, store drafts, or send messages. Omit drafts only for 16 planner template options. Never invent sender facts, prior meetings, attendance, availability or hiring authority.
    ConnectorNo auth
  • List the bio pages (mini sites) belonging to the currently selected team, with their public URL, publish state and setup progress. Use this first when the user mentions "my bio page", "link in bio" or "mini site" — every other mini-site tool takes the siteId this returns (and can omit it entirely when the team has exactly one site).
    ConnectorAPI key
  • Patch the user's active brand profile — voice, themes, expertise areas, personality traits, hashtag set, audience-size estimates, or bio. Useful when the user wants Claude to refine their brand voice based on a transcript, style guide, or competitor analysis without leaving the conversation. Only the active profile is mutated; profile selection / creation must happen in the web app.
    ConnectorAPI key